{"id":"https://openalex.org/W4412378301","doi":"https://doi.org/10.1145/3726302.3730120","title":"\u03bcDS: Multi-Objective Data Snippet Extraction for Dataset Search","display_name":"\u03bcDS: Multi-Objective Data Snippet Extraction for Dataset Search","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412378301","doi":"https://doi.org/10.1145/3726302.3730120"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730120","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730120","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730120","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730120","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103324373","display_name":"Xiao Zhou","orcid":"https://orcid.org/0009-0008-1132-6408"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Zhou","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0009-0008-1132-6408","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003930260","display_name":"Qiaosheng Chen","orcid":"https://orcid.org/0009-0002-0610-7725"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiaosheng Chen","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0009-0002-0610-7725","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102851674","display_name":"Jiageng Chen","orcid":"https://orcid.org/0009-0002-0968-2426"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiageng Chen","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0009-0002-0968-2426","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063617509","display_name":"Gong Cheng","orcid":"https://orcid.org/0000-0003-3539-7776"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gong Cheng","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0003-3539-7776","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18085874,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"116","last_page":"126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/snippet","display_name":"Snippet","score":0.949493408203125},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7447814345359802},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.47534963488578796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35943374037742615},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33050984144210815},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32830965518951416}],"concepts":[{"id":"https://openalex.org/C2777822670","wikidata":"https://www.wikidata.org/wiki/Q1120538","display_name":"Snippet","level":2,"score":0.949493408203125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7447814345359802},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.47534963488578796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35943374037742615},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33050984144210815},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32830965518951416},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3726302.3730120","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730120","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730120","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730120","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730120","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730120","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321605","display_name":"Government of Jiangsu Province","ror":"https://ror.org/004svx814"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412378301.pdf","grobid_xml":"https://content.openalex.org/works/W4412378301.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W2473280987","https://openalex.org/W2537262135","https://openalex.org/W2583371954","https://openalex.org/W2610332888","https://openalex.org/W2901376054","https://openalex.org/W2926805670","https://openalex.org/W2969723769","https://openalex.org/W2980480643","https://openalex.org/W2989319206","https://openalex.org/W3013008430","https://openalex.org/W3021397474","https://openalex.org/W3026889466","https://openalex.org/W3099965312","https://openalex.org/W3100107515","https://openalex.org/W3108941002","https://openalex.org/W3154140311","https://openalex.org/W3164353784","https://openalex.org/W3176140580","https://openalex.org/W3178892021","https://openalex.org/W3180230246","https://openalex.org/W3196904276","https://openalex.org/W3197320265","https://openalex.org/W3204996219","https://openalex.org/W4207007780","https://openalex.org/W4221009220","https://openalex.org/W4284700914","https://openalex.org/W4288086192","https://openalex.org/W4367047277","https://openalex.org/W4386794805","https://openalex.org/W4387332921","https://openalex.org/W4400526175","https://openalex.org/W4400528824","https://openalex.org/W4401023534","https://openalex.org/W4402042501"],"related_works":["https://openalex.org/W1607713096","https://openalex.org/W2798329462","https://openalex.org/W3036724449","https://openalex.org/W2400258664","https://openalex.org/W192970673","https://openalex.org/W2144605188","https://openalex.org/W2146654604","https://openalex.org/W1254682812","https://openalex.org/W2443829582","https://openalex.org/W2122881689"],"abstract_inverted_index":{"With":[0],"the":[1,8,46,65,104],"continuous":[2],"growth":[3],"of":[4,48,115],"open":[5],"data":[6,38,50,82,105],"on":[7,31],"Web,":[9],"dataset":[10,124],"search":[11],"has":[12,52],"become":[13],"a":[14,24,49,86,97,113],"prominent":[15],"specialized":[16],"retrieval":[17],"problem":[18,90],"to":[19,23,123],"find":[20],"datasets":[21,29],"relevant":[22],"query.":[25],"Recent":[26],"solutions":[27],"rank":[28],"based":[30],"not":[32],"only":[33],"their":[34,42],"metadata,":[35],"but":[36],"also":[37],"snippets":[39,106],"extracted":[40,107],"from":[41,55],"actual":[43],"data.":[44],"While":[45],"goodness":[47],"snippet":[51,76],"been":[53],"studied":[54],"various":[56],"aspects,":[57],"in":[58,75],"this":[59],"paper":[60],"we":[61,84],"propose":[62],"to,":[63],"for":[64],"first":[66],"time,":[67],"jointly":[68],"optimize":[69],"compactness,":[70],"relevance,":[71],"representativeness,":[72],"and":[73,91,118],"cohesiveness":[74],"extraction.":[77],"To":[78],"extract":[79],"such":[80],"multi-objective":[81],"snippets,":[83],"formulate":[85],"new":[87],"combinatorial":[88],"optimization":[89],"design":[92],"an":[93],"efficient":[94],"algorithm":[95,110],"with":[96],"proved":[98],"worst-case":[99],"approximation":[100],"ratio.":[101],"We":[102],"evaluate":[103],"by":[108,120],"our":[109],"intrinsically":[111],"through":[112],"set":[114],"quality":[116],"metrics":[117],"extrinsically":[119],"applying":[121],"them":[122],"search.":[125]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}